© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23368
    Prev
    Next
    INDEX
    Explanations

    words related to intentionality or purposeful action

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating intentionality or deliberate actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addons
    -0.85
    soon
    -0.79
     Parables
    -0.75
    esc
    -0.72
     Warrant
    -0.71
     Citation
    -0.69
    anon
    -0.69
    norm
    -0.69
    rose
    -0.68
    ĸļ
    -0.68
    POSITIVE LOGITS
     misleading
    0.87
     misrepresent
    0.84
     mislead
    0.80
     provoking
    0.80
     provocative
    0.79
     misled
    0.78
     sabot
    0.78
     obfusc
    0.78
     dece
    0.75
     sabotage
    0.75
    Activations Density 0.026%

    No Known Activations